Kai Chen 陈恺 SenseTime

About

Kai Chen is a vice director at SenseTime, leading the algorithm platform team of EIG Research (EIG: Emerging Innovations Group, a BG of SenseTime). The team targets at developing state-of-the-art computer vision algorithms for research and applications, and building an advanced platform for training and deployment.
He received the PhD degree in The Chinese University of Hong Kong in 2019, under the supervision of Prof. Dahua Lin and Chen Change Loy at MMLab. Before that, he received the B.Eng. degree from Tsinghua University in 2015.
His research interests include computer vision and deep learning, particularly focusing on object detection, segmentation and video understanding.

We have opening positions for interns and full-time researchers/engineers, see here for details. If you are interested please contact me via email.

CV    Google Scholar    Github

Education

   2015 - present

Ph.D. in Information Engineering
The Chinese University of Hong Kong

   2011 - 2015

B.Eng. in Automation
Tsinghua University

Experience

   2019.02 - 2019.05

Research Intern
Facebook AI Research (FAIR)

News

  •  One paper accepted to ECCV 2020 (Spotlight).
  •  One paper accepted to CVPR 2020.
  •  We won the 1st prize in  COCO 2019 Object Detection Challenge (without external data). (Team: MMDet)
  •  One paper accepted to ICCV 2019 (oral).
  •  Three paper accepted to CVPR 2019.
  •  We released MMCV  and  MMDetection, a high quality object detection codebase.
  •   MMCV: GitHub stars  MMDetection: GitHub stars
  •  We won the  COCO 2018 Object Detection Challenge. (Team: MMDet) (slides)
  •  One paper accepted to CVPR 2018.
  •  One paper accepted to CVPR 2017 (Spotlight).

Publication

Side-Aware Boundary Localization for More Precise Object Detection

Jiaqi Wang, Wenwei Zhang, Yuhang Cao, Kai Chen, Jiangmiao Pang, Tao Gong, Jianping Shi, Chen Change Loy, Dahua Lin
European Conference on Computer Vision (ECCV), 2020 (Spotlight)

[PDF]

Feature Pyramid Grids

Kai Chen, Yuhang Cao, Chen Change Loy, Dahua Lin, Christoph Feichtenhofer
Tech report, arXiv, 2020

[PDF]

Prime Sample Attention in Object Detection

Yuhang Cao, Kai Chen, Chen Change Loy, Dahua Lin
Computer Vision and Pattern Recognition (CVPR), 2020

[PDF]

MMDetection: Open MMLab Detection Toolbox and Benchmark

Kai Chen, Jiaqi Wang*, Jiangmiao Pang*, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jiarui Xu, Zheng Zhang, Dazhi Cheng, Chenchen Zhu, Tianheng Cheng, Qijie Zhao, Buyu Li, Xin Lu, Rui Zhu, Yue Wu, Jifeng Dai, Jingdong Wang, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin
Tech report, arXiv, 2019

[PDF]  [Code]

CARAFE: Content-Aware ReAssembly of FEatures

Jiaqi Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, Dahua Lin
International Conference on Computer Vision (ICCV), 2019 (Oral)

[PDF]  [Code]

Hybrid Task Cascade for Instance Segmentation

Kai Chen, Jiangmiao Pang, Jiaqi Wang, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin
Computer Vision and Pattern Recognition (CVPR), 2019

[PDF]  [Code]

Region Proposal by Guided Anchoring

Jiaqi Wang*, Kai Chen*, Shuo Yang, Chen Change Loy, Dahua Lin
Computer Vision and Pattern Recognition (CVPR), 2019

[PDF]  [Code]

Libra R-CNN: Towards Balanced Learning for Object Detection

Jiangmiao Pang, Kai Chen, Jianping Shi, Huajun Feng, Wanli Ouyang, Dahua Lin
Computer Vision and Pattern Recognition (CVPR), 2019

[PDF]  [Code]

Optimizing Video Object Detection via a Scale-Time Lattice

Kai Chen, Jiaqi Wang, Shuo Yang, Xingcheng Zhang, Yuanjun Xiong, Chen Change Loy, Dahua Lin
Computer Vision and Pattern Recognition (CVPR), 2018

[PDF]  [Project page]  [Code]

Discover and Learn New Objects from Documentaries

Kai Chen, Hang Song, Chen Change Loy, Dahua Lin
Computer Vision and Pattern Recognition (CVPR), 2017 (Spotlight)

[PDF]  [Project page]  [Dataset]

Video Object Segmentation with Re-identification

Xiaoxiao Li, Yuankai Qi, Zhe Wang, Kai Chen, Ziwei Liu, Jianping Shi, Ping Luo, Xiaoou Tang, Chen Change Loy
Workshop of DAVIS Challenge on Video Object Segmentation, Computer Vision and Pattern Recognition (CVPR), 2017 (Winning entry)

[PDF]  [Project page]

Activities

Reviewer/PC Member

  • CVPR, ICCV, ECCV, AAAI, BMVC, ACM MM
  • TPAMI, IJCV, JMLR

Teaching Assistant

  • IERG4080: Building Scalable Internet-based Services
  • IERG3810: Microcontrollers and Embedded Systems Laboratory

Contacts

  • chenkai sensetime.com